Smart Driving Vehicles (SDVs) are assisted by Mobile Edge Computing (MEC) to enhance the ability to deal with complex road conditions. Smart network composed of SDVs and MEC. The transmission of low delay is required in intelligent driving tasks. However, High Mobility Edge Computing Service Hand-Off (HMEC-HO) can cause retransmission delays and some security issues. To reduce delay in Smart network, a Hybrid Transmission and Reputation Management (HTRM) system is presented. Based on Fifth Generation Mobile Communications (5G) Vehicle-to-Everything (V2X) technology, an efficient hybrid Vehicle-to-Vehicle (V2V) and Vehicle-to-Infrastructure (V2I) Scheduling (EH-V2VV2I) algorithm is designed, which uses relay vehicles to help initiating-vehicles for task transmission. To enhance the reliability of V2V connection, an algorithm of Relay Vehicle Selection and Reputation Management (RV-SRM) is proposed for predicting the link survival time, selecting highly reliable relay vehicles, and managing vehicle credibility simultaneously. The simulation results show that HTRM makes the throughput of the tasks of edge server to meet the requirements of vehicles. The experiments show that the delay of our method is reduced by 41% and the reliability of V2V connection is improved by 31% than the hard handover method.

In order for the offshore drilling platform to operate properly, workers need to perform regular maintenance on the platform equipment, but the complex working environment exposes workers to hazards. During inspection and maintenance, the use of personal protective equipment (PPE) such as helmets and workwear can effectively reduce the probability of worker injuries. Existing PPE detection methods are mostly for construction sites and only detect whether helmets are worn or not. This paper proposes a high-precision and high-speed PPE detection method for the offshore drilling platform based on object detection and classification. As a first step, we develop a modified YOLOv4 (named RFA-YOLO)-based object detection model for improving localization and recognition for people, helmets, and workwear. On the basis of the class and coordinates of the object detection output, this paper proposes a method for constructing position features based on the object bounding box to obtain feature vectors characterizing the relative offsets between objects. Then, the classifier is obtained by training a dataset consisting of position features through a random forest algorithm, with parameter optimization. As a final step, the PPE detection is achieved by analyzing the information output from the classifier through an inference mechanism. To evaluate the proposed method, we construct the offshore drilling platform dataset (ODPD) and conduct comparative experiments with other methods. The experimental results show that the method in this paper achieves 13 FPS as well as 93.1% accuracy. Compared to other state-of-the-art models, the proposed PPE detection method performs better on ODPD. The method in this paper can rapidly and accurately identify workers who are not wearing helmets or workwear on the offshore drilling platform, and an intelligent video surveillance system based on this model has been implemented.

Offshore drilling platforms (ODPs) are critical infrastructure for exploring and developing marine oil and gas resources. As these platforms' capabilities expand, deploying intelligent surveillance services to ensure safe production has become increasingly important. However, the unique geographical locations and harsh environmental conditions of ODPs pose significant challenges for processing large volumes of video data, complicating the implementation of efficient surveillance systems. This study proposes a Cloud-Edge Large-Tiny Model Collaborative (CELTC) architecture grounded in deep reinforcement learning to optimize the processing and decision-making of surveillance data in offshore drilling platform scenarios. CELTC architecture leverages edge-cloud computing, deploying complex, high-precision large models on cloud servers and lightweight tiny models on edge devices. This dual deployment strategy capitalizes on tiny models' rapid response and large cloud models' high-precision capabilities. Additionally, the architecture integrates a deep reinforcement learning algorithm designed to optimize the scheduling and offloading of computational tasks between large and tiny models in the cloud-edge environment. The efficacy of the proposed architecture is validated using real-world surveillance data from ODPs through simulations and comparative experiments.

With the evolution of 6G technology, mobile edge computing is rapidly advancing as a crucial application scenario. This research presents an innovative method for vehicle-edge task offloading decision-making, leveraging real-time data inputs such as channel conditions, image entropy, and detector confidence levels. We propose a collaborative task processing framework for vehicle-edge computing that effectively combines lightweight and heavyweight models to cater to varying demands, ensuring efficient task execution. Additionally, the study introduces a custom-designed reinforcement learning algorithm aimed explicitly at optimizing offloading scheduling. This algorithm boosts decision-making accuracy and efficiency and features a comprehensive reward system to achieve a balanced trade-off between detection performance and latency. The frameworks efficacy is thoroughly evaluated in complex driving scenarios using the SODA10M dataset. Our results indicate the frameworks capability to achieve convergence, enhance precision, ensure stability, and maintain a lightweight operation, emphasizing its suitability for real-world implementation. This work provides practical and efficient strategies for intelligent driving task scheduling to meet the requirements of contemporary dynamic environments.

In dynamic IoT system, the device may generate multiple heterogeneous computational tasks, that require CPU and GPU co-processing, in each period. Furthermore, different heterogeneous computing tasks have specific requirements for GPU resource types. Realizing real-time scheduling and processing of large-scale hybrid computing tasks with high heterogeneity and dense quantity has become an urgent problem. First, we propose a cloud-based task processing framework that uses multi-level feedback queues to ensure the fairness of large-scale task parallel computing. Second, we decoupled the original problem into a series of mixed-integer nonlinear programming problems using Lyapunov optimization, aiming to reduce the solution complexity of the real-time scheduling problem. Finally, we propose a multi-agent reinforcement learning algorithm, employing long and short-term memory networks with parameter resetting, to generate task offloading decisions in near real-time based on partially knowable future information. Through extensive simulation experiments, we have demonstrated that our algorithm can reduce the average task processing time by approximately 19.95% and enhance the task processing capability of the IoT system by roughly 12.43%, especially in large-scale hybrid computing task systems.

Achieving real-time processing of tasks has become a crucial objective in the Internet of Vehicles (IoV) field. During the online generation of tasks in IoV systems, many dependency tasks arrive randomly within continuous time frames, and it is impossible to predict the number of arriving tasks and the dependencies between sub-tasks. Offloading dependent tasks, which are quantity-intensive and have complex dependencies, to appropriate vehicle edge servers (VESs) for online processing of large-scale tasks remains a challenge. Firstly, we innovatively propose a VES task parallel processing framework incorporating a multi-level feedback queue to enhance the cross-slot parallel processing capabilities of the IoV system. Secondly, to reduce the complexity of problem-solving, we employ the Lyapunov optimization method to decouple the online task offloading control problem into single-stage mixed-integer nonlinear programming problem. Finally, we design an online task decision-making algorithm based on multi-agent reinforcement learning to achieve real-time task offloading decisions in complex dynamic IoV environments. To validate our algorithm’s superiority in dynamic IoV systems, we compare it with other online task offloading decision-making algorithms. Simulation results show that ours significantly reduces the all-task processing latency of IoV system by 15% compared to the comparison algorithms, and the task average latency time is reduced by 14%.